© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203819
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    м
    1.18
    ر
    1.12
    р
    1.02
    ди
    0.91
    то
    0.90
    로
    0.86
    о
    0.85
    ethe
    0.85
     stressful
    0.84
     respectful
    0.83
    POSITIVE LOGITS
    a
    1.30
    t
    1.02
    ttt
    1.02
    i
    1.01
    ti
    0.98
    া
    0.95
    、
    0.95
    and
    0.93
    tttt
    0.93
    it
    0.91
    Activations Density 0.000%

    No Known Activations